Preparation of Fractal-Inspired Computational Architectures for Advanced Large Language Model Analysis

TL;DR

This paper introduces FractalNet, a fractal-inspired framework for automatically generating and evaluating CNN architectures, demonstrating competitive performance on CIFAR-10 without expensive NAS methods.

Contribution

The paper presents a novel recursive fractal template-based system for systematic CNN architecture exploration that reduces computational costs.

Findings

Generated over 1,200 CNN architectures for CIFAR-10

Achieved up to 80.18% accuracy after five epochs

Demonstrated stable training dynamics with fractal structures

Abstract

This paper proposes FractalNet, a framework based on fractal design principles that automatically generates and evaluates convolutional neural network (CNN) architectures using recursive template patterns. Rather than relying on computationally expensive Neural Architecture Search (NAS) methods, the framework explores a structured architecture space defined by recursive fractal templates that systematically vary key parameters such as fractal depth, column width, and layer configurations. The framework consists of three core components: a generator that produces candidate architectures via controlled permutations of convolutional, normalization, activation, and dropout layers; a fractal template module that enforces recursive multi-path structural patterns; and a runner module that manages model training, evaluation, and logging. Using this system, over 1,200 distinct CNN architectures were automatically generated and evaluated on the CIFAR-10 image classification benchmark. Training was performed in PyTorch using stochastic gradient descent with Automatic Mixed Precision (AMP) and gradient checkpointing to reduce computational overhead. Experimental results demonstrate that fractal-based architectures exhibit stable training dynamics and achieve competitive performance, with an average validation accuracy of 60-70% and a peak accuracy of 80.18% after only five training epochs. These findings suggest that recursive fractal structures provide an effective means of balancing network depth and width while supporting large-scale automated architecture exploration. The proposed framework offers a resource-efficient and interpretable approach to systematic neural architecture experimentation.